Tootfinder

Towards an AI-based knowledge assistant for goat farmers based on Retrieval-Augmented Generation
Nana Han, Dong Liu, Tomas Norton
https://arxiv.org/abs/2509.09848 https://

Towards an AI-based knowledge assistant for goat farmers based on Retrieval-Augmented Generation
Large language models (LLMs) are increasingly being recognised as valuable knowledge communication tools in many industries. However, their application in livestock farming remains limited, being constrained by several factors not least the availability, diversity and complexity of knowledge sources. This study introduces an intelligent knowledge assistant system designed to support health management in farmed goats. Leveraging the Retrieval-Augmented Generation (RAG), two structured knowledge …

SI-FACT: Mitigating Knowledge Conflict via Self-Improving Faithfulness-Aware Contrastive Tuning
Shengqiang Fu
https://arxiv.org/abs/2509.10208 https://arxi…

SI-FACT: Mitigating Knowledge Conflict via Self-Improving Faithfulness-Aware Contrastive Tuning
Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we propose a novel self improving framework,Self Improving Faithfulness Aware Contrastive Tuning.The framework uses a self instruct mechanism that allows the base LLM to automatically generate high quality,structured contrastive learning data,including anchor sampl…

"How Should Diamond Open Access Work for Books?" @ Katina Magazine: https://katinamagazine.org/content/article/open-knowledge/2025/how-should-diamond-oa-work-for-books

Taylor Swift shares some NFL knowledge, plus 2025 season goes off the rails in our Madden simulation

https://www.cbssports.com/nfl/news/taylor-

AI slop and the destruction of knowledge:
We must protect and cultivate the ecosystem of human knowledge. AI models can mimic the appearance of scholarly work, but they are (by construction) unconcerned with truth—the result is a torrential outpouring of unchecked but convincing-sounding “information”. At best, such output is accidentally true, but generally citationless, divorced from human reasoning and the web of scholarship that it steals from. At worst, it is confidently wrong. Bot…

Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation
Xujie Yuan, Shimin Di, Jielong Tang, Libin Zheng, Jian Yin
https://arxiv.org/abs/2508.09460

Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) significantly enhances the reasoning capabilities of LargeLanguage Models by leveraging structured knowledge. However, existing KG-RAG frameworks typically operate as open-loop systems, suffering from cognitive blindness, an inability to recognize their exploration deficiencies. This leads to relevance drift and incomplete evidence, which existing self-refinement methods, designed for unstructured text-based RAG, cannot effectively r…

Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Seyed Muhammad Hossein Mousavi, S. Younes Mirinezhad
https://arxiv.org/abs/2508.09188

Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Affective computing faces a major challenge: the lack of high-quality, diverse depth facial datasets for recognizing subtle emotional expressions. We propose a framework for synthetic depth face generation using an optimized GAN with Knowledge Distillation (EMA teacher models) to stabilize training, improve quality, and prevent mode collapse. We also apply Genetic Algorithms to evolve GAN latent vectors based on image statistics, boosting diversity and visual quality for target emotions. The ap…

Reasoning About Knowledge on Regular Expressions is 2EXPTIME-complete
Avijeet Ghosh, Sujata Ghosh, Fran\c{c}ois Schwarzentruber
https://arxiv.org/abs/2508.09784 https://

Reasoning About Knowledge on Regular Expressions is 2EXPTIME-complete
Logics for reasoning about knowledge and actions have seen many applications in various domains of multi-agent systems, including epistemic planning. Change of knowledge based on observations about the surroundings forms a key aspect in such planning scenarios. Public Observation Logic (POL) is a variant of public announcement logic for reasoning about knowledge that gets updated based on public observations. Each state in an epistemic (Kripke) model is equipped with a set of expected observati…

Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis
Xi Long, Christy Boscardin, Lauren A. Maggio, Joseph A. Costello, Ralph Gonzales, Rasmyah Hammoudeh, Ki Lai, Yoon Soo Park, Brian C. Gin
https://arxiv.org/abs/2508.09458

Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis
Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial Intelligence (AI)-assisted extraction promises efficiency but raises concerns about accuracy, making it critical to distinguish AI 'hallucinations' (fabricated content) from legitimate interpretive differences. We developed an extraction platform using large language m…

KG-Attention: Knowledge Graph-Guided Attention at Test-Time via Bidirectional Information Aggregation
Songlin Zhai, Guilin Qi, Yuan Meng
https://arxiv.org/abs/2507.08704

KG-Attention: Knowledge Graph-Guided Attention at Test-Time via Bidirectional Information Aggregation
Knowledge graphs (KGs) play a critical role in enhancing large language models (LLMs) by introducing structured and grounded knowledge into the learning process. However, most existing KG-enhanced approaches rely on parameter-intensive fine-tuning, which risks catastrophic forgetting and degrades the pretrained model's generalization. Moreover, they exhibit limited adaptability to real-time knowledge updates due to their static integration frameworks. To address these issues, we introduce the f…

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
Haydn Thomas Jones, Natalie Maus, Josh Magnus Ludan, Maggie Ziyu Huan, Jiaming Liang, Marcelo Der Torossian Torres, Jiatao Liang, Zachary Ives, Yoseph Barash, Cesar de la Fuente-Nunez, Jacob R. Gardner, Mark Yatskar
https://arxiv.org/abs/2508.10899

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis we performed on a diverse set of models on the GuacaMol benchmark using supervised classifiers, over 60\% of molecules proposed had high probability of being mutagenic. In this work, we introduce \ourdataset, a dataset of priors for design pr…

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Nojan Sheybani, Alessandro Pegoraro, Jonathan Knauer, Phillip Rieger, Elissa Mollakuqe, Farinaz Koushanfar, Ahmad-Reza Sadeghi
https://arxiv.org/abs/2509.09787

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Split Learning (SL) is a distributed learning approach that enables resource-constrained clients to collaboratively train deep neural networks (DNNs) by offloading most layers to a central server while keeping in- and output layers on the client-side. This setup enables SL to leverage server computation capacities without sharing data, making it highly effective in resource-constrained environments dealing with sensitive data. However, the distributed nature enables malicious clients to manipul…

KP-A: A Unified Network Knowledge Plane for Catalyzing Agentic Network Intelligence
Yun Tang, Mengbang Zou, Zeinab Nezami, Syed Ali Raza Zaidi, Weisi Guo
https://arxiv.org/abs/2507.08164

KP-A: A Unified Network Knowledge Plane for Catalyzing Agentic Network Intelligence
The emergence of large language models (LLMs) and agentic systems is enabling autonomous 6G networks with advanced intelligence, including self-configuration, self-optimization, and self-healing. However, the current implementation of individual intelligence tasks necessitates isolated knowledge retrieval pipelines, resulting in redundant data flows and inconsistent interpretations. Inspired by the service model unification effort in Open-RAN (to support interoperability and vendor diversity), …

Research Awards - 2025 Canadian Friends of Sufi Arts, Culture, and Knowledge (CFSACK)
https://ift.tt/Zx8K92U
University of Alaska - Fairbanks - Alaska & Polar Regions Area Studies Bibliographer & Curator of…
via Input 4 RELCFP

"AI Summaries" have infested #ScienceDirect now with their inaccurate but confidently-formulated statements... Fortunately some people are fighting back, like @… who emailed them about it:

Sources: ByteDance is working on a lightweight MR device that resembles goggles, tethered to a compute puck, and has a team working on the device's custom chips (The Information)
https://www.theinformation.com/articles/bytedance-developin…

ByteDance Developing Mixed Reality Goggles in Challenge to Meta
Competition in mixed reality devices is heating up. TikTok’s parent, ByteDance, is working on a lightweight mixed reality device that resembles a pair of goggles, according to three people with direct knowledge of the project. It’s following in the footsteps of Meta Platforms, which has been ...

LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
Yaoze Zhang, Rong Wu, Pinlong Cai, Xiaoman Wang, Guohang Yan, Song Mao, Ding Wang, Botian Shi
https://arxiv.org/abs/2508.10391

LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
Retrieval-Augmented Generation (RAG) plays a crucial role in grounding Large Language Models by leveraging external knowledge, whereas the effectiveness is often compromised by the retrieval of contextually flawed or incomplete information. To address this, knowledge graph-based RAG methods have evolved towards hierarchical structures, organizing knowledge into multi-level summaries. However, these approaches still suffer from two critical, unaddressed challenges: high-level conceptual summarie…

Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States
Nicholas Carlotti, Mirko Nava, Alessandro Giusti
https://arxiv.org/abs/2509.10405

Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States
We introduce a model for monocular RGB relative pose estimation of a ground robot that trains from scratch without pose labels nor prior knowledge about the robot's shape or appearance. At training time, we assume: (i) a robot fitted with multiple LEDs, whose states are independent and known at each frame; (ii) knowledge of the approximate viewing direction of each LED; and (iii) availability of a calibration image with a known target distance, to address the ambiguity of monocular depth estima…

"How a New Data Platform Sheds Light on #OpenScience #Funding" @ Katina Magazine:

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains
Zilu Dong, Xiangqing Shen, Zinong Yang, Rui Xia
https://arxiv.org/abs/2507.08427 …

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains
Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates. By automatically extracting logical patterns from structured knowledge bases and aligning them with LLMs' internal logics, ChainEdit dynamically generates and edits logically…

Just closed the last open v0.1 release blocking ticket against scopehal-docs!
The docs aren't perfect but we've fixed (to our knowledge) everything preventing an initial release, other than the last minute stuff to make the docs link to the github binary release page etc. (and pushing an updated HTML/PDF copy to the website, which is coming soon along with other website updates like re-rendered screenshots)
This brings the total number of ngscopeclient release blockers do…

US embeds trackers in AI chip shipments to catch diversions to China, sources say
U.S. authorities have secretly placed location tracking devices in targeted shipments of advanced chips they see as being at high risk of illegal diversion to China, according to two people with direct knowledge of the previously unreported law enforcement tactic.
🕵️

South Sudan and Israel
are discussing a deal
to resettle Palestinians
from war-torn Gaza
in the troubled African nation,
three sources told Reuters
- a plan quickly dismissed as unacceptable by Palestinian leaders.
The sources, who have knowledge of the matter but spoke on condition of anonymity,
said no agreement had been reached but talks between South Sudan and Israel were ongoing.
The plan, if carried further,
would envisage pe…

Conformal prediction without knowledge of labeled calibration data
Jonas Flechsig, Maximilian Pilz
https://arxiv.org/abs/2509.10321 https://arxiv.org/pdf/2…

Conformal prediction without knowledge of labeled calibration data
We extend the method of conformal prediction beyond the case relying on labeled calibration data. Replacing the calibration scores by suitable estimates, we identify conformity sets $C$ for classification and regression models that rely on unlabeled calibration data. Given a classification model with accuracy $1-β$, we prove that the conformity sets guarantee a coverage of $P(Y \in C) \geq 1-α-β$ for an arbitrary parameter $α\in (0,1)$. The same coverage guarantee also holds for regression …

Facilitating Personalized TTS for Dysarthric Speakers Using Knowledge Anchoring and Curriculum Learning
Yejin Jeon, Solee Im, Youngjae Kim, Gary Geunbae Lee
https://arxiv.org/abs/2508.10412

Facilitating Personalized TTS for Dysarthric Speakers Using Knowledge Anchoring and Curriculum Learning
Dysarthric speakers experience substantial communication challenges due to impaired motor control of the speech apparatus, which leads to reduced speech intelligibility. This creates significant obstacles in dataset curation since actual recording of long, articulate sentences for the objective of training personalized TTS models becomes infeasible. Thus, the limited availability of audio data, in addition to the articulation errors that are present within the audio, complicates personalized sp…

from my link log —
TLD domain name renewal grace periods.
https://www.namecheap.com/support/knowledgebase/article.aspx/9916/2207/tlds-grace-periods/
saved 2025-09-09

TLDs' grace periods - Domains - Namecheap.com
Learn more about TLDs' grace periods. Find your answers at Namecheap Knowledge Base.

In a short blog post for the MacArthur Foundation, my colleague Veronica Thamaini and I discuss the Abstract Wikipedia proposal, one of five finalists for the ongoing 100&Change program.
A Path to a World Where Everyone Can Share in the Sum of All Knowledge
https://www.

A Path to a World Where Everyone Can Share in the Sum of All Knowledge

A Framework for FAIR and CLEAR Ecological Data and Knowledge: Semantic Units for Synthesis and Causal Modelling
Lars Vogt, Birgitta K\"onig-Ries, Tim Alamenciak, Joshua I. Brian, Carlos Alberto Arnillas, Lotte Korell, Robert Fr\"uhst\"uckl, Tina Heger
https://arxiv.org/abs/2508.08959…

A Framework for FAIR and CLEAR Ecological Data and Knowledge: Semantic Units for Synthesis and Causal Modelling
Ecological research increasingly relies on integrating heterogeneous datasets and knowledge to explain and predict complex phenomena. Yet, differences in data types, terminology, and documentation often hinder interoperability, reuse, and causal understanding. We present the Semantic Units Framework, a novel, domain-agnostic semantic modelling approach applied here to ecological data and knowledge in compliance with the FAIR (Findable, Accessible, Interoperable, Reusable) and CLEAR (Cognitively…

Our English-language MA program in #ReligiousStudies attracts students from all over the world. Sometimes it can be a challenge to handle the diversity of undergrad training and disciplinary knowledge that our students bring with them. But this semester’s “ethics and politics of religious heritage” class was a delight. After a brief introduction, I let my students bring their topics, texts,…

KI-Update kompakt: KI auf der IFA, ChatGPT, Gemini-Lernhilfe, World Knowledge
Das "KI-Update" liefert werktäglich eine Zusammenfassung der wichtigsten KI-Entwicklungen.
https://www.

AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design
Zihao Chen, Ji Zhuang, Jinyi Shen, Xiaoyue Ke, Xinyi Yang, Mingjie Zhou, Zhuoyao Du, Xu Yan, Zhouyang Wu, Zhenyu Xu, Jiangli Huang, Li Shang, Xuan Zeng, Fan Yang
https://arxiv.org/abs/2508.10409

AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design
In this paper, we propose AnalogSeeker, an effort toward an open-source foundation language model for analog circuit design, with the aim of integrating domain knowledge and giving design assistance. To overcome the scarcity of data in this field, we employ a corpus collection strategy based on the domain knowledge framework of analog circuits. High-quality, accessible textbooks across relevant subfields are systematically curated and cleaned into a textual domain corpus. To address the complex…

I don't want any of those to be illegal but I always keep in my mind the fact that the overwhelming majority of wagering opportunities/solicitations come from profitable businesses whose core business is making winning wagers with people whose lesser knowledge and resources put them at deep disadvantages.
I'm not big on wagering...

This is awesome! 🤩
From: @…
https://mastodon.social/@arstechnica/114851881549053554

Ars Technica (@arstechnica@mastodon.social)
Attached: 1 image Two guys hated using Comcast, so they built their own fiber ISP Brothers-in-law use construction knowledge to compete against Comcast in Michigan. https://arstechnica.com/tech-policy/2025/07/two-guys-hated-using-comcast-so-they-built-their-own-fiber-isp/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social

https://www.bbc.com/news/articles/ce8307ge49eo
Meta response to random bans (and extreme slander, i believe) is "watchagunnadoaboutit".
And you know what? They're right, because they're powerful and uncaring and safe in the knowledge they'll face no repe…

Anger and confusion as Meta overturns more Instagram account bans
Hundreds of people have contacted the BBC to say they have wrongly been shut out of their accounts.

Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
Sahil Sethi, Kai Sundmacher, Caroline Ganzer
https://arxiv.org/abs/2509.10273

Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
Ionic liquids (ILs) have emerged as versatile replacements for traditional solvents because their physicochemical properties can be precisely tailored to various applications. However, accurately predicting key thermophysical properties remains challenging due to the vast chemical design space and the limited availability of experimental data. In this study, we present a data-driven transfer learning framework that leverages a neural recommender system (NRS) to enable reliable property predicti…

Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research
Rashid Mushkani
https://arxiv.org/abs/2508.07507 https://arxiv.…

Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research
Transdisciplinary approaches are increasingly essential for addressing grand societal challenges, particularly in complex domains such as Artificial Intelligence (AI), urban planning, and social sciences. However, effectively validating and integrating knowledge across distinct epistemic and ontological perspectives poses significant difficulties. This article proposes a six-dimensional framework for assessing and strengthening transdisciplinary knowledge validity in AI and city studies, based …

The @… meetup is now on YouTube!
As a community, we're committed to sharing knowledge and expertise in PHP development. Our channel will feature recordings of our meetup sessions, so you can learn from the best and stay up-to-date on the latest industry trends. Help us grow our community by sharing this post with your network and subscribing to our channe…

I've archived 2 forums on Autodesk's site related to the RV player. There's a big banner on top that these have been temporarily restored in read-only mode. Apparently ADSK shut them down and in doing so disappeared a large knowledge base for their products.
They'll disappear again sooner or later and there is a frustratingly low amount of developer info about #RV and

Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledge
Mohammad Saqib Hasan, Sayontan Ghosh, Dhruv Verma, Geoff Kuenning, Erez Zadok, Scott A. Smolka, Niranjan Balasubramanian
https://arxiv.org/abs/2509.08808

Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledge
We study the problem of Open-Vocabulary Constructs(OVCs) -- ones not known beforehand -- in the context of converting natural language (NL) specifications into formal languages (e.g., temporal logic or code). Models fare poorly on OVCs due to a lack of necessary knowledge a priori. In such situations, a domain expert can provide correct constructs at inference time based on their preferences or domain knowledge. Our goal is to effectively reuse this inference-time, expert-provided knowledge for…

There's only one week left to apply for the position of CEO of Wikimedia Netherlands. Is open knowledge your default, spreek je een aardig woordje Nederlands and do you have the experience we are looking for? Send us a note https://www.wikimedia.nl/directeur/

Querying Climate Knowledge: Semantic Retrieval for Scientific Discovery
Mustapha Adamu, Qi Zhang, Huitong Pan, Longin Jan Latecki, Eduard C. Dragut
https://arxiv.org/abs/2509.10087

Querying Climate Knowledge: Semantic Retrieval for Scientific Discovery
The growing complexity and volume of climate science literature make it increasingly difficult for researchers to find relevant information across models, datasets, regions, and variables. This paper introduces a domain-specific Knowledge Graph (KG) built from climate publications and broader scientific texts, aimed at improving how climate knowledge is accessed and used. Unlike keyword based search, our KG supports structured, semantic queries that help researchers discover precise connections…

Entropy and Learning of Lipschitz Functions under Log-Concave Measures
Pierre Bizeul, Boaz Klartag
https://arxiv.org/abs/2509.10355 https://arxiv.org/pdf/2…

Entropy and Learning of Lipschitz Functions under Log-Concave Measures
We study regression of $1$-Lipschitz functions under a log-concave measure $μ$ on $\mathbb{R}^d$. We focus on the high-dimensional regime where the sample size $n$ is subexponential in $d$, in which distribution-free estimators are ineffective. We analyze two polynomial-based procedures: the projection estimator, which relies on knowledge of an orthogonal polynomial basis of $μ$, and the least-squares estimator over low-degree polynomials, which requires no knowledge of $μ$ whatsoever. Their…

A Rule-Based Approach to Specifying Preferences over Conflicting Facts and Querying Inconsistent Knowledge Bases
Meghyn Bienvenu, Camille Bourgaux, Katsumi Inoue, Robin Jean
https://arxiv.org/abs/2508.07742

A Rule-Based Approach to Specifying Preferences over Conflicting Facts and Querying Inconsistent Knowledge Bases
Repair-based semantics have been extensively studied as a means of obtaining meaningful answers to queries posed over inconsistent knowledge bases (KBs). While several works have considered how to exploit a priority relation between facts to select optimal repairs, the question of how to specify such preferences remains largely unaddressed. This motivates us to introduce a declarative rule-based framework for specifying and computing a priority relation between conflicting facts. As the express…

"Ultimately, engaging the public enriches our scholarship. It pushes us to think more carefully about clarity, ethics, and relevance. It also ensures that the knowledge we produce contributes to a wider societal good, affirming the role of the university not just as a place of knowledge production, but also of public service."
#OpenScience
https://social.edu.nl/@Bibliothecaris/114833640819292319

It's easy to build a website, and difficult to build a website that has to be up for more than four years.
(Four years is roughly the point when some kind of migration is unavoidable, and a service where the functional knowledge has been lost will just get switched off or completely replaced.)

Entanglement certification from moments of positive maps
Qing-Hua Zhang, Xiaoyu Ma, Shao-Ming Fei
https://arxiv.org/abs/2508.09766 https://arxiv.org/pdf/25…

Entanglement certification from moments of positive maps
Entanglement certification is crucial in physical experiments, particularly when only partial knowledge of the quantum state is available. In this context, we present an entanglement criterion based on positive but not completely positive maps, which eliminates the need to identify eigenvalues of the output state. Notably, the Faddeev-LeVerrier algorithm establishes a relationship between the coefficients of characteristic polynomials and the moments of a matrix. This enables the existence of n…

Cowboys and guard Tyler Smith agree on $96 million extension, AP sources say https://www.foxsports.com/articles/nfl/cowboys-and-guard-tyler-smith-agree-on-96-million-extension-ap-sources-say

Source: cloud startup Vercel has been approached by investors offering to invest hundreds of millions at an $8B-$9B valuation; it was valued at $3B last year (The Information)
https://www.theinformation.com/articles/cloud-startup-vercel-fields-o…

Cloud Startup Vercel Fields Offers for $9 Billion Valuation
Vercel, a nine-year-old cloud startup that companies use to host and develop websites and artificial intelligence apps, has been approached by investors offering to invest hundreds of millions of dollars at a valuation between $8 billion to $9 billion, according to a person with direct knowledge ...

The value of conceptual knowledge
Benjamin Davies, Anirudh Sankar
https://arxiv.org/abs/2509.09170 https://arxiv.org/pdf/2509.09170

The value of conceptual knowledge
We formalize what it means to have conceptual knowledge about a statistical decision-making environment. Such knowledge tells agents about the structural relationships among unknown, payoff-relevant states. It allows agents to represent states as combinations of features. Conceptual knowledge is more valuable when states are more "reducible": when their prior variances are explained by fewer features. Its value is non-monotone in the quantity and quality of available data, and vanishes with inf…

The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference
Ma\"el Jullien, Marco Valentino, Andr\'e Freitas
https://arxiv.org/abs/2508.10777

The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference
Large language models are often assumed to acquire increasingly structured, generalizable internal representations simply by scaling data and parameters. We interrogate this assumption by introducing a Clinical Trial Natural Language Inference benchmark comprising four reasoning families, Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction. Each item is paired with a targeted Ground Knowledge and Meta-Level Reasoning Verification (GKMRV) probe, allowi…

Digital gazetteers: review and prospects for place name knowledge bases
Kalana Wijegunarathna, Kristin Stock, Christopher B. Jones
https://arxiv.org/abs/2507.08553

Digital gazetteers: review and prospects for place name knowledge bases
Gazetteers typically store data on place names, place types and the associated coordinates. They play an essential role in disambiguating place names in online geographical information retrieval systems for navigation and mapping, detecting and disambiguating place names in text, and providing coordinates. Currently there are many gazetteers in use derived from many sources, with no commonly accepted standard for encoding the data. Most gazetteers are also very limited in the extent to which th…

Knowledge Graph-Based approach for Sustainable 6G End-to-End System Design
Akshay Jain, Sylvaine Kerboeuf, Sokratis Barmpounakis, Crist\'obal Vinagre Z., Stefan Wendt, Dinh Thai Bui, Pol Alemany, Riccardo Nicolicchia, Jos\'e Mar\'ia Jorquera Valero, Dani Korpi, Mohammad Hossein Moghaddam, Mikko A. Uusitalo, Patrik Rugeland, Abdelkader Outtagarts, Karthik Upadhya, Panagiotis Demestichas, Raul Mu\~noz, Manuel Gil P\'erez, Daniel Adanza, Ricard Vilalta

Knowledge Graph-Based approach for Sustainable 6G End-to-End System Design
Previous generations of cellular communication, such as 5G, have been designed with the objective of improving key performance indicators (KPIs) such as throughput, latency, etc. However, to meet the evolving KPI demands as well as the ambitious sustainability targets for the ICT industry, 6G will need to be designed differently. Concretely, 6G will need to consider both the performance and sustainability targets for the various use cases it will serve. Moreover, like previous generations, 6G w…

What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Evgeny Kharlamov, Steffen Staab
https://arxiv.org/abs/2508.08344

What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include questions that can be directly answered using existing triples in KG, making it unclear whether models perform reasoning or simply retrieve answers directly. Moreover, inconsistent evaluation metrics …

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Hui Li, Pengfei Yang, Juanyang Chen, Le Dong, Yanxin Chen, Quan Wang
https://arxiv.org/abs/2507.07015

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and statistical heterogeneities, failing to leverage the complementary prior knowledge embedded in cross-modal teacher models. This paper empirically reveals two critical issues in existing approaches: distillation path selection and knowledge drift. To address …

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu, Yuchuan Wu, Fan Shi, Lei Liao, Jinghui Lu, Xiaodong Ge, Han Wang, Minghan Zhuo, Xuecheng Wu, Xiang Fei, Hao Feng, Guozhi Tang, An-Lan Wang, Hanshen Zhu, Yangfan He, Quanhuan Liang, Liyuan Meng, Chao Feng, Can Huang, Jingqun Tang, Bin Li
https://

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we p…

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
Stanley Ngugi
https://arxiv.org/abs/2508.07075

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
Large Language Models (LLMs) struggle with dynamic knowledge updates, especially when new information conflicts with deeply embedded facts. Such conflicting factual edits often lead to two critical issues: resistance to adopting the new fact and severe catastrophic forgetting of unrelated knowledge. This paper introduces and evaluates a novel "unlearn-then-learn" strategy for precise knowledge editing in LLMs, leveraging the parameter-efficient fine-tuning (PEFT) technique, Infused Adapter by I…

FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs
Xueli Pan, Victor de Boer, Jacco van Ossenbruggen
https://arxiv.org/abs/2508.10467 …

FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs
Question answering over Scholarly Knowledge Graphs (SKGs) remains a challenging task due to the complexity of scholarly content and the intricate structure of these graphs. Large Language Model (LLM) approaches could be used to translate natural language questions (NLQs) into SPARQL queries; however, these LLM-based approaches struggle with SPARQL query generation due to limited exposure to SKG-specific content and the underlying schema. We identified two main types of errors in the LLM-generat…

WATCH: Aaron Rodgers refuses to sign for 'autograph hound' after testing his NFL game knowledge

https://www.cbssports.com/nfl/news/watch-a

Eat your own KR: a KR-based approach to index Semantic Web Endpoints and Knowledge Graphs
Pierre Maillot (WIMMICS), Catherine Faron (UniCA, I3S, WIMMICS), Fabien Gandon (WIMMICS), Franck Michel (Laboratoire I3S - SPARKS, WIMMICS), Pierre Monnin (WIMMICS)
https://arxiv.org/abs/2508.08713

Eat your own KR: a KR-based approach to index Semantic Web Endpoints and Knowledge Graphs
Over the last decade, knowledge graphs have multiplied, grown, and evolved on the World Wide Web, and the advent of new standards, vocabularies, and application domains has accelerated this trend. IndeGx is a framework leveraging an extensible base of rules to index the content of KGs and the capacities of their SPARQL endpoints. In this article, we show how knowledge representation (KR) and reasoning methods and techniques can be used in a reflexive manner to index and characterize existing kn…

Koza and Koza-Hub for born-interoperable knowledge graph generation using KGX
Daniel R Korn, Patrick Golden, Aaron Odell, Katherina Cortes, Shilpa Sundar, Kevin Schaper, Sarah Gehrke, Corey Cox, Harry Caufield, Justin Reese, Evan Morris, Christopher J Mungall, Melissa Haendel
https://arxiv.org/abs/2509.09096

Koza and Koza-Hub for born-interoperable knowledge graph generation using KGX
Knowledge graph construction has become an essential domain for the future of biomedical research. But current approaches demand a high amount of redundant labor. These redundancies are the result of the lack of data standards and "knowledge-graph ready" data from sources. Using the KGX standard, we aim to solve these issues. Herein we introduce Koza and the Koza-Hub, a Python software package which streamlines ingesting raw biomedical information into the KGX format, and an associated set of c…

Research Awards - 2025 Canadian Friends of Sufi Arts, Culture, and Knowledge (CFSACK)
https://ift.tt/a83UWXG
University of Alaska - Fairbanks - Alaska & Polar Regions Area Studies Bibliographer & Curator of…
via Input 4 RELCFP

RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
Bhavik Agarwal, Hemant Sunil Jomraj, Simone Kaplunov, Jack Krolick, Viktoria Rojkova
https://arxiv.org/abs/2508.09893

RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
Regulatory compliance question answering (QA) requires precise, verifiable information, and domain-specific expertise, posing challenges for Large Language Models (LLMs). In this work, we present a novel multi-agent framework that integrates a Knowledge Graph (KG) of Regulatory triplets with Retrieval-Augmented Generation (RAG) to address these demands. First, agents build and maintain an ontology-free KG by extracting subject--predicate--object (SPO) triplets from regulatory documents and syst…

Cowboys sign guard Tyler Smith to $96 million, 4-year extension, AP sources say https://www.foxsports.com/articles/nfl/cowboys-sign-guard-tyler-smith-to-96-million-4year-extension-ap-sources-say

When Is Prior Knowledge Helpful? Exploring the Evaluation and Selection of Unsupervised Pretext Tasks from a Neuro-Symbolic Perspective
Lin-Han Jia, Si-Yu Han, Wen-Chao Hu, Jie-Jing Shao, Wen-Da Wei, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li
https://arxiv.org/abs/2508.07299

When Is Prior Knowledge Helpful? Exploring the Evaluation and Selection of Unsupervised Pretext Tasks from a Neuro-Symbolic Perspective
Neuro-symbolic (Nesy) learning improves the target task performance of models by enabling them to satisfy knowledge, while semi/self-supervised learning (SSL) improves the target task performance by designing unsupervised pretext tasks for unlabeled data to make models satisfy corresponding assumptions. We extend the Nesy theory based on reliable knowledge to the scenario of unreliable knowledge (i.e., assumptions), thereby unifying the theoretical frameworks of SSL and Nesy. Through rigorous t…

TASC: Task-Aware Shared Control for Teleoperated Manipulation
Ze Fu, Pinhao Song, Yutong Hu, Renaud Detry
https://arxiv.org/abs/2509.10416 https://arxiv.or…

TASC: Task-Aware Shared Control for Teleoperated Manipulation
We present TASC, a Task-Aware Shared Control framework for teleoperated manipulation that infers task-level user intent and provides assistance throughout the task. To support everyday tasks without predefined knowledge, TASC constructs an open-vocabulary interaction graph from visual input to represent functional object relationships, and infers user intent accordingly. A shared control policy then provides rotation assistance during both grasping and object interaction, guided by spatial cons…

The past few months of hand-coding MastoGizmos and RSS Gizmos have both given me more knowledge and more comfort around working with CSS,
so last week I decided to see if I could create a single-page application that would allow the user to both find information about a person listed on Wikipedia and create informed, context-added searches of external sources like Google News, Bing, and Chronicling America.
And y’all, I think I made something pretty nice.
I haven’t put all m…

ExDoS: Expert-Guided Dual-Focus Cross-Modal Distillation for Smart Contract Vulnerability Detection
Yifan Jia, Ye Tian, Yanbin Wang, Jianguo Sun, Haitao Xu
https://arxiv.org/abs/2509.10252

ExDoS: Expert-Guided Dual-Focus Cross-Modal Distillation for Smart Contract Vulnerability Detection
The success of smart contracts has made them a target for attacks, but their closed-source nature often forces vulnerability detection to work on bytecode, which is inherently more challenging than source-code-based analysis. While recent studies try to align source and bytecode embeddings during training to transfer knowledge, current methods rely on graph-level alignment that obscures fine-grained structural and semantic correlations between the two modalities. Moreover, the absence of precis…

Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code
Muhammad Haseeb
https://arxiv.org/abs/2508.08322 https://

Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code
Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, NotebookLM-based document synthesis for contextual unde…

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
Zhenye Yang, Jinpeng Chen, Huan Li, Xiongnan Jin, Xuanyang Li, Junwei Zhang, Hongbo Gao, Kaimin Wei, Senzhang Wang
https://arxiv.org/abs/2508.10669

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
Conversational recommender systems (CRSs) aim to proactively capture user preferences through natural language dialogue and recommend high-quality items. To achieve this, CRS gathers user preferences via a dialog module and builds user profiles through a recommendation module to generate appropriate recommendations. However, existing CRS faces challenges in capturing the deep semantics of user preferences and dialogue context. In particular, the efficient integration of external knowledge graph…

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
Rui Lu, Zhenyu Hou, Zihan Wang, Hanchen Zhang, Xiao Liu, Yujiang Li, Shi Feng, Jie Tang, Yuxiao Dong
https://arxiv.org/abs/2509.10446

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon reasoning capacity with browsing tools and the lack of sufficiently difficult supervised data. To address these challenges, we present DeepDive to advance deep search agents. First, we propose a strategy to automatically synthesize complex, difficult, and hard-…

DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images
Haoran Sun, Haoyu Bian, Shaoning Zeng, Yunbo Rao, Xu Xu, Lin Mei, Jianping Gou
https://arxiv.org/abs/2507.08648

DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images
Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless, real-world data are obviously more valuable comparing to artificially intelligence generated data, particularly in constructing image datasets. For this reason, we propose a novel method for auto-constructing datasets from real-world images by a multiagent colla…

This Week in Sports Trivia: August 14, 2025 https://www.nytimes.com/athletic/6551336/2025/08/14/this-week-in-sports-trivia-august-14-2025/

Source: Nvidia is scaling back DGX Cloud to primarily internal R&D use; DGX Cloud was initially envisioned to compete with major cloud providers like AWS (Anissa Gardizy/The Information)
https://www.theinformation.com/articles/nvidia-steps-back-cloud-ef…

Nvidia Steps Back From Cloud Effort to Compete with AWS
Nvidia is stepping back from its nascent cloud computing business, which had put it in quasi-competition with Amazon Web Services. It has lessened its efforts to attract businesses to the cloud service, dubbed DGX Cloud, said a person with direct knowledge of the situation. Instead, Nvidia plans ...

Membership and Memorization in LLM Knowledge Distillation
Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu, Yifeng Cai, Hamed Haddadi
https://arxiv.org/abs/2508.07054 https://

Membership and Memorization in LLM Knowledge Distillation
Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ''teacher'' to a smaller ''student'' model. However, students may inherit the teacher's privacy when the teacher is trained on private data. In this work, we systematically characterize and investigate membership and memorization privacy risks inherent in six LLM KD techniques. Using instruction-tuning settings that span seven NLP t…

Distillation versus Contrastive Learning: How to Train Your Rerankers
Zhichao Xu, Zhiqi Huang, Shengyao Zhuang, Ashim Gupta, Vivek Srikumar
https://arxiv.org/abs/2507.08336

Distillation versus Contrastive Learning: How to Train Your Rerankers
Training text rerankers is crucial for information retrieval. Two primary strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger reranker). While both have been studied in the literature, a clear comparison of their effectiveness for training cross-encoder rerankers under practical conditions is needed. This paper empirically compares these strategies by training rerankers of different size…

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
Soumia Mehimeh
https://arxiv.org/abs/2508.09277 https://…

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
Value function initialization (VFI) is an effective way to achieve a jumpstart in reinforcement learning (RL) by leveraging value estimates from prior tasks. While this approach is well established in tabular settings, extending it to deep reinforcement learning (DRL) poses challenges due to the continuous nature of the state-action space, the noisy approximations of neural networks, and the impracticality of storing all past models for reuse. In this work, we address these challenges and intro…

Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
Luyao Tang, Kunze Huang, Chaoqi Chen, Yuxuan Yuan, Chenxin Li, Xiaotong Tu, Xinghao Ding, Yue Huang
https://arxiv.org/abs/2508.10731

Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
Human perceptual systems excel at inducing and recognizing objects across both known and novel categories, a capability far beyond current machine learning frameworks. While generalized category discovery (GCD) aims to bridge this gap, existing methods predominantly focus on optimizing objective functions. We present an orthogonal solution, inspired by the human cognitive process for novel object understanding: decomposing objects into visual primitives and establishing cross-knowledge comparis…

Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering
Hanna Abi Akl
https://arxiv.org/abs/2509.10249

Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering
Recent advances in Language Models (LMs) have failed to mask their shortcomings particularly in the domain of reasoning. This limitation impacts several tasks, most notably those involving ontology engineering. As part of a PhD research, we investigate the consequences of incorporating formal methods on the performance of Small Language Models (SLMs) on reasoning tasks. Specifically, we aim to orient our work toward using SLMs to bootstrap ontology construction and set up a series of preliminar…

CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
Julia Gastinger, Christian Meilicke, Heiner Stuckenschmidt
https://arxiv.org/abs/2509.09474 https…

CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
We address the task of temporal knowledge graph (TKG) forecasting by introducing a fully explainable method based on temporal rules. Motivated by recent work proposing a strong baseline using recurrent facts, our approach learns four simple types of rules with a confidence function that considers both recency and frequency. Evaluated on nine datasets, our method matches or surpasses the performance of eight state-of-the-art models and two baselines, while providing fully interpretable predictio…

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
Vaibhav Chaudhary, Neha Soni, Narotam Singh, Amita Kapoor
https://arxiv.org/abs/2509.09272

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
Knowledge graphs, a powerful tool for structuring information through relational triplets, have recently become the new front-runner in enhancing question-answering systems. While traditional Retrieval Augmented Generation (RAG) approaches are proficient in fact-based and local context-based extraction from concise texts, they encounter limitations when addressing the thematic and holistic understanding of complex, extensive texts, requiring a deeper analysis of both text and context. This pape…

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang
https://arxiv.org/abs/2508.10433

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data…

Bio-KGvec2go: Serving up-to-date Dynamic Biomedical Knowledge Graph Embeddings
Hamid Ahmad, Heiko Paulheim, Rita T. Sousa
https://arxiv.org/abs/2509.07905 https://

Bio-KGvec2go: Serving up-to-date Dynamic Biomedical Knowledge Graph Embeddings
Knowledge graphs and ontologies represent entities and their relationships in a structured way, having gained significance in the development of modern AI applications. Integrating these semantic resources with machine learning models often relies on knowledge graph embedding models to transform graph data into numerical representations. Therefore, pre-trained models for popular knowledge graphs and ontologies are increasingly valuable, as they spare the need to retrain models for different tas…

A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering
Chenliang Zhang, Lin Wang, Yuanyuan Lu, Yusheng Qi, Kexin Wang, Peixu Hou, Wenshi Chen
https://arxiv.org/abs/2508.10337

A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering
This paper describes the solutions of the Dianping-Trust-Safety team for the META CRAG-MM challenge. The challenge requires building a comprehensive retrieval-augmented generation system capable for multi-modal multi-turn question answering. The competition consists of three tasks: (1) answering questions using structured data retrieved from an image-based mock knowledge graph, (2) synthesizing information from both knowledge graphs and web search results, and (3) handling multi-turn conversati…

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
Yi Liu, Xiangrong Zhu, Xiangyu Liu, Wei Wei, Wei Hu
https://arxiv.org/abs/2509.07555 h…

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
In a rapidly evolving world where information updates swiftly, knowledge in large language models (LLMs) becomes outdated quickly. Retraining LLMs is not a cost-effective option, making knowledge editing (KE) without modifying parameters particularly necessary. We find that although existing retrieval-augmented generation (RAG)-based KE methods excel at editing simple knowledge, they struggle with KE in multi-hop question answering due to the issue of "edit skipping", which refers to skipping t…

Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Technical Solutions
Parsa Omidi, Xingshuai Huang, Axel Laborieux, Bahareh Nikpour, Tianyu Shi, Armaghan Eshaghi
https://arxiv.org/abs/2508.10824

Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Technical Solutions
Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context retention, continual learning, and knowledge integration. This review presents a unified framework bridging neuroscience principles, including dynamic multi-timescale memory, selective attention, and consolidation, with engineering advances in Memory-Augment…

Towards Explainable Job Title Matching: Leveraging Semantic Textual Relatedness and Knowledge Graphs
Vadim Zadykian, Bruno Andrade, Haithem Afli
https://arxiv.org/abs/2509.09522

Towards Explainable Job Title Matching: Leveraging Semantic Textual Relatedness and Knowledge Graphs
Semantic Textual Relatedness (STR) captures nuanced relationships between texts that extend beyond superficial lexical similarity. In this study, we investigate STR in the context of job title matching - a key challenge in resume recommendation systems, where overlapping terms are often limited or misleading. We introduce a self-supervised hybrid architecture that combines dense sentence embeddings with domain-specific Knowledge Graphs (KGs) to improve both semantic alignment and explainability…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/3]:
- Knowledge-based Consistency Testing of Large Language Models
Sai Sathiesh Rajan, Ezekiel Soremekun, Sudipta Chattopadhyay

Automated Creation of the Legal Knowledge Graph Addressing Legislation on Violence Against Women: Resource, Methodology and Lessons Learned
Claudia dAmato, Giuseppe Rubini, Francesco Didio, Donato Francioso, Fatima Zahra Amara, Nicola Fanizzi
https://arxiv.org/abs/2508.06368

Automated Creation of the Legal Knowledge Graph Addressing Legislation on Violence Against Women: Resource, Methodology and Lessons Learned
Legal decision-making process requires the availability of comprehensive and detailed legislative background knowledge and up-to-date information on legal cases and related sentences/decisions. Legal Knowledge Graphs (KGs) would be a valuable tool to facilitate access to legal information, to be queried and exploited for the purpose, and to enable advanced reasoning and machine learning applications. Indeed, legal KGs may act as knowledge intensive component to be used by pre-dictive machine le…

ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
Shu Zhao, Tan Yu, Anbang Xu, Japinder Singh, Aaditya Shukla, Rama Akkiraju
https://arxiv.org/abs/2508.09303

ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
Reasoning-augmented search agents such as Search-R1, trained via reinforcement learning with verifiable rewards (RLVR), demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources. These agents address the limitations of their parametric memory by dynamically gathering relevant facts to address complex reasoning tasks. However, existing approaches suffer from a fundamental architectural limitation: they process search queries strictly sequentially, ev…

Is In-Context Learning Learning?
Adrian de Wynter
https://arxiv.org/abs/2509.10414 https://arxiv.org/pdf/2509.10414…

Is In-Context Learning Learning?
In-context learning (ICL) allows some autoregressive models to solve tasks via next-token prediction and without needing further training. This has led to claims about these model's ability to solve (learn) unseen tasks with only a few shots (exemplars) in the prompt. However, deduction does not always imply learning, as ICL does not explicitly encode a given observation. Instead, the models rely on their prior knowledge and the exemplars given, if any. We argue that, mathematically, ICL does c…

KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment
Jiyao Zhang, Chengli Zhong, Hui Xu, Qige Li, Yi Zhou
https://arxiv.org/abs/2507.08665

KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment
Modern large language models (LLMs) show promising progress in formalizing informal mathematics into machine-verifiable theorems. However, these methods still face bottlenecks due to the limited quantity and quality of multilingual parallel corpora. In this paper, we propose a novel neuro-symbolic framework KELPS (Knowledge-Equation based Logical Processing System) to address these problems. KELPS is an iterative framework for translating, synthesizing, and filtering informal data into multiple…

GenOM: Ontology Matching with Description Generation and Large Language Model
Yiping Song, Jiaoyan Chen, Renate A. Schmidt
https://arxiv.org/abs/2508.10703 https://

GenOM: Ontology Matching with Description Generation and Large Language Model
Ontology matching (OM) plays an essential role in enabling semantic interoperability and integration across heterogeneous knowledge sources, particularly in the biomedical domain which contains numerous complex concepts related to diseases and pharmaceuticals. This paper introduces GenOM, a large language model (LLM)-based ontology alignment framework, which enriches the semantic representations of ontology concepts via generating textual definitions, retrieves alignment candidates with an embe…

Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
Seokgi Lee
https://arxiv.org/abs/2508.09755 https://arxiv.org/…

Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of single-hop subquestions that guide document retrieval. This decomposition mitigates the ambiguity inherent in multi-hop queries by clearly targeting distinct knowledge facets. Second, instead of embedding raw or chunked documents directly, we generate answerable questions from ea…

Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
Zhixiang Su, Di Wang, Chunyan Miao
https://arxiv.org/abs/2507.07595

Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
Recent investigations on the effectiveness of Graph Neural Network (GNN)-based models for link prediction in Knowledge Graphs (KGs) show that vanilla aggregation does not significantly impact the model performance. In this paper, we introduce a novel method, named Context Pooling, to enhance GNN-based models' efficacy for link predictions in KGs. To our best of knowledge, Context Pooling is the first methodology that applies graph pooling in KGs. Additionally, Context Pooling is first-of-its-ki…

An Integrated Framework of Prompt Engineering and Multidimensional Knowledge Graphs for Legal Dispute Analysis
Mingda Zhang, Na Zhao, Jianglong Qing, Qing xu, Kaiwen Pan, Ting luo
https://arxiv.org/abs/2507.07893

An Integrated Framework of Prompt Engineering and Multidimensional Knowledge Graphs for Legal Dispute Analysis
The rapid development of artificial intelligence has positioned large language models as fundamental components of intelligent legal systems. However, these models face significant limitations in legal dispute analysis, including insufficient legal knowledge representation, limited concept understanding, and reasoning deficiencies. This research proposes an enhanced framework integrating prompt engineering with multidimensional knowledge graphs. The framework introduces a three-stage hierarchic…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/3]:
- Polish-English medical knowledge transfer: A new benchmark and results
{\L}ukasz Grzybowski, Jakub Pokrywka, Micha{\l} Ciesi\'o{\l}ka, Jeremi I. Kaczmarek, Marek Kubis

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
Xiaolin Chen, Xuemeng Song, Haokun Wen, Weili Guan, Xiangyu Zhao, Liqiang Nie
https://arxiv.org/abs/2509.07817

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
Textual response generation is pivotal for multimodal \mbox{task-oriented} dialog systems, which aims to generate proper textual responses based on the multimodal context. While existing efforts have demonstrated remarkable progress, there still exist the following limitations: 1) \textit{neglect of unstructured review knowledge} and 2) \textit{underutilization of large language models (LLMs)}. Inspired by this, we aim to fully utilize dual knowledge (\textit{i.e., } structured attribute and un…

How well can LLMs provide planning feedback in grounded environments?
Yuxuan Li, Victor Zhong
https://arxiv.org/abs/2509.09790 https://arxiv.org/pdf/2509.0…

How well can LLMs provide planning feedback in grounded environments?
Learning to plan in grounded environments typically requires carefully designed reward functions or high-quality annotated demonstrations. Recent works show that pretrained foundation models, such as large language models (LLMs) and vision language models (VLMs), capture background knowledge helpful for planning, which reduces the amount of reward design and demonstrations needed for policy learning. We evaluate how well LLMs and VLMs provide feedback across symbolic, language, and continuous c…

MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection
Alexandru-Andrei Avram, Adrian Groza, Alexandru Lecu
https://arxiv.org/abs/2508.10143 https://

MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection
The large spread of disinformation across digital platforms creates significant challenges to information integrity. This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles, focusing on titles and short text snippets. The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent (which relies on named entity recognition), (iii) a coherence detection agent (u…

Compartmentalised Agentic Reasoning for Clinical NLI
Ma\"el Jullien, Lei Xu, Marco Valentino, Andr\'e Freitas
https://arxiv.org/abs/2509.10222 https://

Compartmentalised Agentic Reasoning for Clinical NLI
A common assumption holds that scaling data and parameters yields increasingly structured, generalisable internal representations. We interrogate this assumption in clinical natural language inference (NLI) by adopting a benchmark decomposed into four reasoning families, Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction, and introducing CARENLI, a Compartmentalised Agentic Reasoning for Clinical NLI that separates knowledge access from principled in…